Difference between revisions of "CTAB-Map"

From IntRoLab
Line 67: Line 67:
 
Community data sets from other loop closure detection approaches :
 
Community data sets from other loop closure detection approaches :
 
* Angeli et al. : [http://cogrob.ensta.fr/loopclosure.html Lip6Indoor and Lip6Outdoor]
 
* Angeli et al. : [http://cogrob.ensta.fr/loopclosure.html Lip6Indoor and Lip6Outdoor]
* FAB-MAP : [http://www.robots.ox.ac.uk/~mobile/IJRR_2008_Dataset NewCollege and CityCentre]
+
* Cummins et al. (FAB-MAP) : [http://www.robots.ox.ac.uk/~mobile/IJRR_2008_Dataset NewCollege and CityCentre]
 
</english>
 
</english>
 
<french>
 
<french>

Revision as of 15:07, 26 January 2011

CTAB-Map : Constant-Time Appearance-Based Mapping

Description[edit]

Loop closure detection is the process involved when trying to find a match between the current and a previously visited locations in SLAM (Simultaneous Localization And Mapping). Over time, the amount of time required to process new observations increases with the size of the internal map, which may affect real-time processing. CTAB-Map is a novel real-time loop closure detection approach for large-scale and long-term SLAM. Our approach is based on efficient memory management to keep computation time for each new observation under a fixed time limit, thus achieving O(1) complexity. Results demonstrate the approach's adaptability and scalability using one custom data set and four standard data sets.

Results[edit]

Summary of the loop closures detected on UdeS1Hz data set :

  • Green : Loop closures detected
  • Yellow : Loop closures rejected
  • Red : Unable to detect a loop closure because old places could not be retrieved

CTAB-Map LoopClosureMapResults.png

Processing time for each image acquired (real-time limit fixed to 700 ms):

CTAB-Map LoopClosureTimeResults.png


Source code[edit]

The code was tested on Windows (Xp, 7), Mac OS X 10.6 and Ubuntu 10.4LTS.


UdeS1Hz data set[edit]

Community data sets from other loop closure detection approaches :


Publications

Labbé, M., Michaud, F. (2011), “Memory management approach for real-time appearance-based loop closure detection,” To appear in IEEE Transactions on Robotics.